SpanQuery下的子类有好几个,我就放一篇里集中说说。SpanQuery即跨度查询,首先要理解跨度这个概念,Lucene里跨度是用Spans这个类定义的,源码如下:
/** Expert: an enumeration of span matches. Used to implement span searching.
* Each span represents a range of term positions within a document. Matches
* are enumerated in order, by increasing document number, within that by
* increasing start position and finally by increasing end position. */
public abstract class Spans {
/** Move to the next match, returning true iff any such exists. */
public abstract boolean next() throws IOException;
/** Skips to the first match beyond the current, whose document number is
* greater than or equal to <i>target</i>.
* <p>The behavior of this method is <b>undefined</b> when called with
* <code> target ≤ current</code>, or after the iterator has exhausted.
* Both cases may result in unpredicted behavior.
* <p>Returns true iff there is such
* a match. <p>Behaves as if written: <pre class="prettyprint">
* boolean skipTo(int target) {
* do {
* if (!next())
* return false;
* } while (target > doc());
* return true;
* }
* </pre>
* Most implementations are considerably more efficient than that.
*/
public abstract boolean skipTo(int target) throws IOException;
/** Returns the document number of the current match. Initially invalid. */
public abstract int doc();
/** Returns the start position of the current match. Initially invalid. */
public abstract int start();
/** Returns the end position of the current match. Initially invalid. */
public abstract int end();
/**
* Returns the payload data for the current span.
* This is invalid until {@link #next()} is called for
* the first time.
* This method must not be called more than once after each call
* of {@link #next()}. However, most payloads are loaded lazily,
* so if the payload data for the current position is not needed,
* this method may not be called at all for performance reasons. An ordered
* SpanQuery does not lazy load, so if you have payloads in your index and
* you do not want ordered SpanNearQuerys to collect payloads, you can
* disable collection with a constructor option.<br>
* <br>
* Note that the return type is a collection, thus the ordering should not be relied upon.
* <br/>
* @lucene.experimental
*
* @return a List of byte arrays containing the data of this payload, otherwise null if isPayloadAvailable is false
* @throws IOException if there is a low-level I/O error
*/
// TODO: Remove warning after API has been finalized
public abstract Collection<byte[]> getPayload() throws IOException;
/**
* Checks if a payload can be loaded at this position.
* <p/>
* Payloads can only be loaded once per call to
* {@link #next()}.
*
* @return true if there is a payload available at this position that can be loaded
*/
public abstract boolean isPayloadAvailable() throws IOException;
/**
* Returns the estimated cost of this spans.
* <p>
* This is generally an upper bound of the number of documents this iterator
* might match, but may be a rough heuristic, hardcoded value, or otherwise
* completely inaccurate.
*/
public abstract long cost();
}
跨度里包含了匹配Term的起始位置和结束位置信息以及跨度价值估算值以及payload信息等等。
首先要说的就是SpanTermQuery,他和TermQuery用法很相似,唯一区别就是SapnTermQuery可以得到Term的span跨度信息,用法如下:
package com.yida.framework.lucene5.query;
import java.io.IOException;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.TextField;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.index.Term;
import org.apache.lucene.index.IndexWriterConfig.OpenMode;
import org.apache.lucene.search.AutomatonQuery;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.MultiTermQuery;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.search.spans.SpanQuery;
import org.apache.lucene.search.spans.SpanTermQuery;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.RAMDirectory;
import org.apache.lucene.util.automaton.Automata;
import org.apache.lucene.util.automaton.Automaton;
/**
* SpanTermQuery用法测试
* @author Lanxiaowei
*
*/
public class SpanTermQueryTest {
public static void main(String[] args) throws IOException {
Directory dir = new RAMDirectory();
Analyzer analyzer = new StandardAnalyzer();
IndexWriterConfig iwc = new IndexWriterConfig(analyzer);
iwc.setOpenMode(OpenMode.CREATE);
IndexWriter writer = new IndexWriter(dir, iwc);
Document doc = new Document();
doc.add(new TextField("text", "the quick brown fox jumps over the lazy dog", Field.Store.YES));
writer.addDocument(doc);
doc = new Document();
doc.add(new TextField("text", "the quick red fox jumps over the sleepy cat", Field.Store.YES));
writer.addDocument(doc);
doc = new Document();
doc.add(new TextField("text", "the quick brown fox jumps over the lazy dog", Field.Store.YES));
writer.addDocument(doc);
writer.close();
IndexReader reader = DirectoryReader.open(dir);
IndexSearcher searcher = new IndexSearcher(reader);
String queryString = "red";
SpanQuery query = new SpanTermQuery(new Term("text",queryString));
TopDocs results = searcher.search(query, null, 100);
ScoreDoc[] scoreDocs = results.scoreDocs;
for (int i = 0; i < scoreDocs.length; ++i) {
//System.out.println(searcher.explain(query, scoreDocs[i].doc));
int docID = scoreDocs[i].doc;
Document document = searcher.doc(docID);
String path = document.get("text");
System.out.println("text:" + path);
}
}
}
SpanNearQuery:用来匹配两个Term之间的跨度的,即一个Term经过几个跨度可以到达另一个Term,slop为跨度因子,用来限制两个Term之间的最大跨度,不可能一个Term和另一个Term之间要经过十万八千个跨度才到达也算两者相近,这不符合常理。所以有个slop因子进行限制。还有一个inOrder参数要引起注意,它用来设置是否允许进行倒序跨度,什么意思?即TermA到TermB不一定是从左到右去匹配也可以从右到左,而从右到左就是倒序,inOrder为true即表示order(顺序)很重要不能倒序去匹配必须正向去匹配,false则反之。注意停用词不在slop统计范围内。
Slop的理解很重要:
在默认情况下slop的值是0, 就相当于TermQuery的精确匹配, 通过设置slop参数(比如"one five"匹配"one two three four five"就需要slop=3,如果slop=2就无法得到结果。这里我们可以认为slope是单词移动得次数,可以左移或者右移。这里特别提 醒,PhraseQuery不保证前后单词的次序,在上面的例子中,"two one"就需要2个slop,也就是认为one 向左边移动2位, 就是能够匹配的”one two”如果是“five three one” 就需要slope=6才能匹配。
还有一个collectPayloads参数表示是否收集payload信息,关于payload后面再单独说。
SpanNearQuery的构造函数如下:
public SpanNearQuery(SpanQuery[] clauses, int slop, boolean inOrder, boolean collectPayloads) {
// copy clauses array into an ArrayList
this.clauses = new ArrayList<>(clauses.length);
for (int i = 0; i < clauses.length; i++) {
SpanQuery clause = clauses[i];
if (field == null) { // check field
field = clause.getField();
} else if (clause.getField() != null && !clause.getField().equals(field)) {
throw new IllegalArgumentException("Clauses must have same field.");
}
this.clauses.add(clause);
}
this.collectPayloads = collectPayloads;
this.slop = slop;
this.inOrder = inOrder;
}
SpanNearQuery使用示例:
/**
* SpanNearQuery测试
* @author Lanxiaowei
*
*/
public class SpanNearQueryTest {
public static void main(String[] args) throws IOException {
Directory dir = new RAMDirectory();
Analyzer analyzer = new StandardAnalyzer();
IndexWriterConfig iwc = new IndexWriterConfig(analyzer);
iwc.setOpenMode(OpenMode.CREATE);
IndexWriter writer = new IndexWriter(dir, iwc);
Document doc = new Document();
doc.add(new TextField("text", "the quick brown fox jumps over the lazy dog", Field.Store.YES));
writer.addDocument(doc);
doc = new Document();
doc.add(new TextField("text", "the quick red fox jumps over the sleepy cat", Field.Store.YES));
writer.addDocument(doc);
doc = new Document();
doc.add(new TextField("text", "the quick brown fox jumps over the lazy dog", Field.Store.YES));
writer.addDocument(doc);
writer.close();
IndexReader reader = DirectoryReader.open(dir);
IndexSearcher searcher = new IndexSearcher(reader);
String queryStringStart = "dog";
String queryStringEnd = "quick";
SpanQuery queryStart = new SpanTermQuery(new Term("text",queryStringStart));
SpanQuery queryEnd = new SpanTermQuery(new Term("text",queryStringEnd));
SpanQuery spanNearQuery = new SpanNearQuery(
new SpanQuery[] {queryStart,queryEnd}, 6, false, false);
TopDocs results = searcher.search(spanNearQuery, null, 100);
ScoreDoc[] scoreDocs = results.scoreDocs;
for (int i = 0; i < scoreDocs.length; ++i) {
//System.out.println(searcher.explain(query, scoreDocs[i].doc));
int docID = scoreDocs[i].doc;
Document document = searcher.doc(docID);
String path = document.get("text");
System.out.println("text:" + path);
}
}
}
示例中dog要到达quick需要经过6个跨度,需要从右至左倒序匹配,所以inOrder设置为false,如果设置为true会导致查询不出来数据。
SpanNotQuery:使用场景是当使用SpanNearQuery时,如果两个Term从TermA到TermB有多种情况,即可能出现TermA或者TermB在索引中重复出现,则可能有多种情况,SpanNotQuery就是用来限制TermA和TermB之间不存在TermC,从而排除一些情况,实现更精确的控制。默认SpanNotQuery的构造函数是这样的:
/** Construct a SpanNotQuery matching spans from <code>include</code> which
* have no overlap with spans from <code>exclude</code>.*/
public SpanNotQuery(SpanQuery include, SpanQuery exclude) {
this(include, exclude, 0, 0);
}
显然这里的第一个参数include应该是SpanNearQuery,第二个参数就是用来做排除的。
SpanNotQuery另一个重载构造函数如下:
/** Construct a SpanNotQuery matching spans from <code>include</code> which
* have no overlap with spans from <code>exclude</code> within
* <code>dist</code> tokens of <code>include</code>. */
public SpanNotQuery(SpanQuery include, SpanQuery exclude, int dist) {
this(include, exclude, dist, dist);
}
它多加了一个dist参数,官方的解释是:Construct a SpanNotQuery matching spans from include
which have no overlap with spans from exclude
within dist
tokens of include
. 说白了就是,使用exclude限制以后匹配到以后,TermA和TermB之间间隔的字符长度做个限制,这就是dist的作用。
SpanNotQuery还有一个更复杂的构造函数重载:
/** Construct a SpanNotQuery matching spans from <code>include</code> which
* have no overlap with spans from <code>exclude</code> within
* <code>pre</code> tokens before or <code>post</code> tokens of <code>include</code>. */
public SpanNotQuery(SpanQuery include, SpanQuery exclude, int pre, int post) {
this.include = include;
this.exclude = exclude;
this.pre = (pre >=0) ? pre : 0;
this.post = (post >= 0) ? post : 0;
if (include.getField() != null && exclude.getField() != null && !include.getField().equals(exclude.getField()))
throw new IllegalArgumentException("Clauses must have same field.");
}
最后一个post参数其实就是dist,pre参数就是限制exclude Term前面有几个字符。这样解释太抽象,用示例代码来说明吧:
package com.yida.framework.lucene5.query;
import java.io.IOException;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.TextField;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.index.Term;
import org.apache.lucene.index.IndexWriterConfig.OpenMode;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.search.spans.SpanNearQuery;
import org.apache.lucene.search.spans.SpanNotQuery;
import org.apache.lucene.search.spans.SpanQuery;
import org.apache.lucene.search.spans.SpanTermQuery;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.RAMDirectory;
/**
* SpanNotQuery测试
* @author Lanxiaowei
*
*/
public class SpanNotQueryTest {
public static void main(String[] args) throws IOException {
Directory dir = new RAMDirectory();
Analyzer analyzer = new StandardAnalyzer();
IndexWriterConfig iwc = new IndexWriterConfig(analyzer);
iwc.setOpenMode(OpenMode.CREATE);
IndexWriter writer = new IndexWriter(dir, iwc);
Document doc = new Document();
doc.add(new TextField("text", "the quick brown fox jumps over the lazy dog", Field.Store.YES));
writer.addDocument(doc);
doc = new Document();
doc.add(new TextField("text", "the quick red fox jumps over the sleepy cat", Field.Store.YES));
writer.addDocument(doc);
doc = new Document();
doc.add(new TextField("text", "the quick brown fox quick gox jumps over the lazy dog", Field.Store.YES));
writer.addDocument(doc);
doc = new Document();
doc.add(new TextField("text", "the quick brown adult slave nice fox winde felt testcase gox quick jumps over the lazy dog", Field.Store.YES));
writer.addDocument(doc);
doc = new Document();
doc.add(new TextField("text", "the quick brown fox quick jumps over the lazy dog", Field.Store.YES));
writer.addDocument(doc);
writer.close();
IndexReader reader = DirectoryReader.open(dir);
IndexSearcher searcher = new IndexSearcher(reader);
String queryStringStart = "dog";
String queryStringEnd = "quick";
String excludeString = "fox";
SpanQuery queryStart = new SpanTermQuery(new Term("text",queryStringStart));
SpanQuery queryEnd = new SpanTermQuery(new Term("text",queryStringEnd));
SpanQuery excludeQuery = new SpanTermQuery(new Term("text",excludeString));
SpanQuery spanNearQuery = new SpanNearQuery(
new SpanQuery[] {queryStart,queryEnd}, 12, false, false);
SpanNotQuery spanNotQuery = new SpanNotQuery(spanNearQuery, excludeQuery, 4,3);
TopDocs results = searcher.search(spanNotQuery, null, 100);
ScoreDoc[] scoreDocs = results.scoreDocs;
for (int i = 0; i < scoreDocs.length; ++i) {
//System.out.println(searcher.explain(query, scoreDocs[i].doc));
int docID = scoreDocs[i].doc;
Document document = searcher.doc(docID);
String path = document.get("text");
System.out.println("text:" + path);
}
}
}
示例代码意思就是查询dog和quick之间没有fox的索引文档,自己运行示例代码参悟吧。
SpanOrQuery顾名思义就是把多个Span'Query用or连接起来,其实你也可以用BooleanQuery来代替SpanOrQuery,但SpanOrQuery会返回额外的Span跨度信息,它的构造函数如下:
SpanOrQuery(SpanQuery... clauses)
接收多个SpanQuery对象并用or连接起来,下面是SpanOrQuery示例代码:
package com.yida.framework.lucene5.query;
import java.io.IOException;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.TextField;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.index.Term;
import org.apache.lucene.index.IndexWriterConfig.OpenMode;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.search.spans.SpanNearQuery;
import org.apache.lucene.search.spans.SpanNotQuery;
import org.apache.lucene.search.spans.SpanOrQuery;
import org.apache.lucene.search.spans.SpanQuery;
import org.apache.lucene.search.spans.SpanTermQuery;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.RAMDirectory;
/**
* SpanOrQuery测试
* @author Lanxiaowei
*
*/
public class SpanOrQueryTest {
public static void main(String[] args) throws IOException {
Directory dir = new RAMDirectory();
Analyzer analyzer = new StandardAnalyzer();
IndexWriterConfig iwc = new IndexWriterConfig(analyzer);
iwc.setOpenMode(OpenMode.CREATE);
IndexWriter writer = new IndexWriter(dir, iwc);
Document doc = new Document();
doc.add(new TextField("text", "the quick brown fox jumps over the lazy dog", Field.Store.YES));
writer.addDocument(doc);
doc = new Document();
doc.add(new TextField("text", "the quick red fox jumps over the sleepy cat", Field.Store.YES));
writer.addDocument(doc);
doc = new Document();
doc.add(new TextField("text", "the quick brown fox quick gox jumps over the lazy dog", Field.Store.YES));
writer.addDocument(doc);
doc = new Document();
doc.add(new TextField("text", "the quick brown adult slave nice fox winde felt testcase gox quick jumps over the lazy dog", Field.Store.YES));
writer.addDocument(doc);
doc = new Document();
doc.add(new TextField("text", "the quick brown adult sick slave nice fox winde felt testcase fox quick jumps over the lazy dog", Field.Store.YES));
writer.addDocument(doc);
doc = new Document();
doc.add(new TextField("text", "the quick brown fox quick jumps over the lazy dog", Field.Store.YES));
writer.addDocument(doc);
writer.close();
IndexReader reader = DirectoryReader.open(dir);
IndexSearcher searcher = new IndexSearcher(reader);
String queryStringStart = "dog";
String queryStringEnd = "quick";
String excludeString = "fox";
String termString = "sick";
SpanQuery queryStart = new SpanTermQuery(new Term("text",queryStringStart));
SpanQuery queryEnd = new SpanTermQuery(new Term("text",queryStringEnd));
SpanQuery excludeQuery = new SpanTermQuery(new Term("text",excludeString));
SpanQuery spanNearQuery = new SpanNearQuery(
new SpanQuery[] {queryStart,queryEnd}, 12, false, false);
SpanNotQuery spanNotQuery = new SpanNotQuery(spanNearQuery, excludeQuery, 4,3);
SpanQuery spanTermQuery = new SpanTermQuery(new Term("text",termString));
SpanOrQuery spanOrQuery = new SpanOrQuery(spanNotQuery,spanTermQuery);
TopDocs results = searcher.search(spanOrQuery, null, 100);
ScoreDoc[] scoreDocs = results.scoreDocs;
for (int i = 0; i < scoreDocs.length; ++i) {
//System.out.println(searcher.explain(query, scoreDocs[i].doc));
int docID = scoreDocs[i].doc;
Document document = searcher.doc(docID);
String path = document.get("text");
System.out.println("text:" + path);
}
}
}
SpanMultiTermQueryWrapper:就是一个Query转换器,用于把MultiTermQuery包装转换成SpanQuery的,具体使用示例,我贴下官方API里提供的示例代码吧:
WildcardQuery wildcard = new WildcardQuery(new Term("field", "bro?n"));
SpanQuery spanWildcard = new SpanMultiTermQueryWrapper<WildcardQuery>(wildcard);
SpanPositionRangeQuery:这个query是用来限制匹配的情况是否分布在(start,end)这个区间内,区间索引从零开始计算,拿示例代码说话,
package com.yida.framework.lucene5.query;
import java.io.IOException;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.TextField;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.index.Term;
import org.apache.lucene.index.IndexWriterConfig.OpenMode;
import org.apache.lucene.search.FuzzyQuery;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.search.spans.SpanMultiTermQueryWrapper;
import org.apache.lucene.search.spans.SpanNearQuery;
import org.apache.lucene.search.spans.SpanNotQuery;
import org.apache.lucene.search.spans.SpanPositionRangeQuery;
import org.apache.lucene.search.spans.SpanQuery;
import org.apache.lucene.search.spans.SpanTermQuery;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.RAMDirectory;
/**
* SpanPositionRangeQuery测试
* @author Lanxiaowei
*
*/
public class SpanPositionRangeQueryTest {
public static void main(String[] args) throws IOException {
Directory dir = new RAMDirectory();
Analyzer analyzer = new StandardAnalyzer();
IndexWriterConfig iwc = new IndexWriterConfig(analyzer);
iwc.setOpenMode(OpenMode.CREATE);
IndexWriter writer = new IndexWriter(dir, iwc);
Document doc = new Document();
doc.add(new TextField("text", "quick brown fox", Field.Store.YES));
writer.addDocument(doc);
doc = new Document();
doc.add(new TextField("text", "jumps over lazy broun dog", Field.Store.YES));
writer.addDocument(doc);
doc = new Document();
doc.add(new TextField("text", "jumps over extremely very lazy broxn dog", Field.Store.YES));
writer.addDocument(doc);
writer.close();
IndexReader reader = DirectoryReader.open(dir);
IndexSearcher searcher = new IndexSearcher(reader);
FuzzyQuery fq = new FuzzyQuery(new Term("text", "broan"));
SpanQuery sfq = new SpanMultiTermQueryWrapper<FuzzyQuery>(fq);
SpanPositionRangeQuery spanPositionRangeQuery = new SpanPositionRangeQuery(sfq, 3, 5);
TopDocs results = searcher.search(spanPositionRangeQuery, null, 100);
ScoreDoc[] scoreDocs = results.scoreDocs;
for (int i = 0; i < scoreDocs.length; ++i) {
//System.out.println(searcher.explain(query, scoreDocs[i].doc));
int docID = scoreDocs[i].doc;
Document document = searcher.doc(docID);
String path = document.get("text");
System.out.println("text:" + path);
}
}
}
稍微解释下上面的代码,首先呢,FuzzyQuery fq = new FuzzyQuery(new Term("text", "broan"));用来查询包含跟单词broan相似字符的索引文档,显然第一个索引文档不符合排除了一个,然后呢,我们new了一个SpanQuery包装器Wrapper,把FuzzyQuery转换成了SpanQuery,然后使用SpanPositionRangeQuery对匹配到的2种情况的落放的位置进行限制即跟broan相似的单词必须分布在(3,5)这个区间内,显然第3个索引文档是分布在(3,6)这个区间内,所以第3个索引文档被排除了,最后只返回第2个索引文档。
SpanPositionRangeQuery还有个子类SpanFirstQuery,其实SpanFirstQuery只不过是把SpanPositionRangeQuery构造函数里的start参数值设置为0,仅此而已,所以不用多说,你也懂的,它的构造函数如下:
SpanFirstQuery(SpanQuery match, int end)
Construct a SpanFirstQuery matching spans in match whose end position is less than or equal to end.
这也就是为什么只有一个end,没有start,因为start默认为零,看源码:
SpanFirstQuery示例我就不提供了,略过。
最后一个要说的就是FieldMaskingSpanQuery,它用于在多个域之间查询,即把另一个域看作某个域,从而看起来就像在同一个域里查询,因为Lucene默认某个条件只能作用在单个域上,不支持跨域查询只能在同一个域里查询,所以有了FieldMaskingSpanQuery,,下面是示例代码:
package com.yida.framework.lucene5.query;
import java.io.IOException;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.index.IndexWriterConfig.OpenMode;
import org.apache.lucene.index.Term;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.search.spans.FieldMaskingSpanQuery;
import org.apache.lucene.search.spans.SpanNearQuery;
import org.apache.lucene.search.spans.SpanQuery;
import org.apache.lucene.search.spans.SpanTermQuery;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.RAMDirectory;
/**
* FieldMaskingSpanQuery测试
* @author Lanxiaowei
*
*/
public class FieldMaskingSpanQueryTest {
public static void main(String[] args) throws IOException {
Directory dir = new RAMDirectory();
Analyzer analyzer = new StandardAnalyzer();
IndexWriterConfig iwc = new IndexWriterConfig(analyzer);
iwc.setOpenMode(OpenMode.CREATE);
IndexWriter writer = new IndexWriter(dir, iwc);
Document doc = new Document();
doc.add(new Field("teacherid", "1", Field.Store.YES, Field.Index.NOT_ANALYZED));
doc.add(new Field("studentfirstname", "james", Field.Store.YES, Field.Index.NOT_ANALYZED));
doc.add(new Field("studentsurname", "jones", Field.Store.YES, Field.Index.NOT_ANALYZED));
writer.addDocument(doc);
//teacher2
doc = new Document();
doc.add(new Field("teacherid", "2", Field.Store.YES, Field.Index.NOT_ANALYZED));
doc.add(new Field("studentfirstname", "james", Field.Store.YES, Field.Index.NOT_ANALYZED));
doc.add(new Field("studentsurname", "smith", Field.Store.YES, Field.Index.NOT_ANALYZED));
doc.add(new Field("studentfirstname", "sally", Field.Store.YES, Field.Index.NOT_ANALYZED));
doc.add(new Field("studentsurname", "jones", Field.Store.YES, Field.Index.NOT_ANALYZED));
writer.addDocument(doc);
writer.close();
IndexReader reader = DirectoryReader.open(dir);
IndexSearcher searcher = new IndexSearcher(reader);
SpanQuery q1 = new SpanTermQuery(new Term("studentfirstname", "james"));
SpanQuery q2 = new SpanTermQuery(new Term("studentsurname", "jones"));
SpanQuery q2m = new FieldMaskingSpanQuery(q2, "studentfirstname");
Query query = new SpanNearQuery(new SpanQuery[]{q1, q2m}, -1, false);
TopDocs results = searcher.search(query, null, 100);
ScoreDoc[] scoreDocs = results.scoreDocs;
for (int i = 0; i < scoreDocs.length; ++i) {
//System.out.println(searcher.explain(query, scoreDocs[i].doc));
int docID = scoreDocs[i].doc;
Document document = searcher.doc(docID);
String teacherid = document.get("teacherid");
System.out.println("teacherid:" + teacherid);
}
}
}
OK,SpanQuery就说这么多,接下来要说的就是PhraseQuery。
如果你还有什么问题请加我Q-Q:7-3-6-0-3-1-3-0-5,
或者加裙一起交流学习!